{"id":"https://openalex.org/W2021775343","doi":"https://doi.org/10.1109/asru.2013.6707704","title":"Acoustic modeling using transform-based phone-cluster adaptive training","display_name":"Acoustic modeling using transform-based phone-cluster adaptive training","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2021775343","doi":"https://doi.org/10.1109/asru.2013.6707704","mag":"2021775343"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028956985","display_name":"Vimal Manohar","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Vimal Manohar","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India","[Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, India]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"[Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, India]","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081270246","display_name":"C. Srinivas","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. Bhargav Srinivas","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, Tamil Nadu, IN","[Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, India]"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, Tamil Nadu, IN","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"[Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, India]","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Umesh","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India","[Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, India]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"[Dept. of Electr. Eng., Indian Inst. of Technol. Madras, Chennai, India]","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028956985"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":2.8854,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91328081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8095626831054688},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7798991203308105},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7369017601013184},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6601118445396423},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.6463353037834167},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5899313688278198},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5087879300117493},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.490405797958374},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.48103076219558716},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4687747061252594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4610975980758667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4216427803039551},{"id":"https://openalex.org/keywords/linear-interpolation","display_name":"Linear interpolation","score":0.4132072925567627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39547157287597656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095626831054688},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7798991203308105},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7369017601013184},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6601118445396423},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6463353037834167},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5899313688278198},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5087879300117493},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.490405797958374},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.48103076219558716},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4687747061252594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4610975980758667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4216427803039551},{"id":"https://openalex.org/C171836373","wikidata":"https://www.wikidata.org/wiki/Q2266329","display_name":"Linear interpolation","level":3,"score":0.4132072925567627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39547157287597656},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2013.6707704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W72757270","https://openalex.org/W1524333225","https://openalex.org/W1805340023","https://openalex.org/W1981706894","https://openalex.org/W2041823554","https://openalex.org/W2069631319","https://openalex.org/W2101965210","https://openalex.org/W2136879537","https://openalex.org/W2151402979","https://openalex.org/W2151484683","https://openalex.org/W2161347627","https://openalex.org/W2165108269","https://openalex.org/W6602923018","https://openalex.org/W6631362777","https://openalex.org/W6682194319"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W1980381208","https://openalex.org/W2025614924","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2550260012","https://openalex.org/W2151402979","https://openalex.org/W2153098279","https://openalex.org/W2160650576"],"abstract_inverted_index":{"In":[0,15],"this":[1,16],"paper,":[2],"we":[3],"propose":[4],"a":[5,44,106],"new":[6],"acoustic":[7],"modeling":[8],"technique":[9],"called":[10],"the":[11,18,26,55,64,73,87,98,112,121,124],"Phone-Cluster":[12],"Adaptive":[13,57],"Training.":[14],"approach,":[17],"parameters":[19,71,118],"of":[20,29,43,72,111],"context-dependent":[21],"states":[22],"are":[23,35,75],"obtained":[24,37],"by":[25,38],"linear":[27,41],"interpolation":[28,83],"several":[30],"monophone":[31],"cluster":[32],"models,":[33],"which":[34],"themselves":[36],"adaptation":[39,62],"using":[40,115],"transformation":[42],"canonical":[45],"Gaussian":[46,66],"Mixture":[47,67],"Model":[48,68,103],"(GMM).":[49],"This":[50],"approach":[51,93],"is":[52],"inspired":[53],"from":[54],"Cluster":[56],"Training":[58],"(CAT)":[59],"for":[60],"speaker":[61],"and":[63,105,123],"Subspace":[65],"(SGMM).":[69],"The":[70,82,91],"model":[74],"updated":[76],"in":[77],"an":[78],"adaptive":[79],"training":[80],"framework.":[81],"vectors":[84],"implicitly":[85],"capture":[86],"phonetic":[88],"context":[89],"information.":[90],"proposed":[92],"shows":[94],"substantial":[95],"improvement":[96],"over":[97],"Continuous":[99],"Density":[100],"Hidden":[101],"Markov":[102],"(CDHMM)":[104],"similar":[107],"performance":[108],"to":[109],"that":[110],"SGMM,":[113],"while":[114],"significantly":[116],"fewer":[117],"than":[119],"both":[120],"CDHMM":[122],"SGMM.":[125]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}